Neural networks carry out chemical simulations in record time
Researchers at the Universities of Vienna and Göttingen have succeeded in developing a method for predicting molecular infrared spectra based on artificial intelligence. These chemical “fingerprints” could only be simulated by common prediction techniques for small molecules in high quality. With the help of the new technology, which is based on neuronal networks similar to the human brain and is therefore capable of learning, the team led by Philipp Marquetand from the Faculty of Chemistry at the University of Vienna was able to carry out simulations that were previously not possible. The potential of this new strategy has now been published in the current issue of the journal “Chemical Science”.
Drastic advances in research of artificial intelligence have led to a wide range of fascinating developments in this area over the last decade. Autonomously driven cars, but also everyday applications such as search engines and spam filters illustrate the versatility of methods from the field of artificial intelligence.
Infrared spectroscopy is one of the most valuable experimental methods to gain insight into the world of molecules. Infrared spectra are chemical fingerprints that provide information on the composition and properties of substances and materials. In many cases, these spectra are very complex – a detailed analysis makes computer-aided simulations indispensable. While quantum chemical calculations in principle enable extremely precise prediction of infrared spectra, their applicability in practice is made difficult by the high computational effort associated with them. For this reason, reliable infrared spectra can only be calculated for relatively small chemical systems.
An international group of researchers led by Philipp Marquetand from the Faculty of Chemistry at the University of Vienna has now found a way to accelerate these simulations using artificial intelligence. For this purpose, so-called artificial neural networks are used, mathematical models of the human brain. These are able to learn the complex quantum mechanical relationships that are necessary for the modelling of infrared spectra by using only a few examples. In this way, the scientists can carry out simulations within a few minutes, which would otherwise take thousands of years even with modern supercomputers – without sacrificing reliability. “We can now finally simulate chemical problems that could not be overcome with the simulation techniques used up to now,” says Michael Gastegger, the first author of the study.
Based on the results of this study, the researchers are confident that their method of spectra prediction will be widely used in the analysis of experimental infrared spectra in the future.
Learn more: Artificial intelligence for obtaining chemical fingerprints
The Latest on: Chemical fingerprints
[google_news title=”” keyword=”chemical fingerprints” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
- Plant sensors could act as an early warning system for farmerson April 17, 2024 at 6:20 am
Using a pair of sensors made from carbon nanotubes, researchers from MIT and the Singapore-MIT Alliance for Research and Technology (SMART) have discovered signals that reveal when plans are ...
- New aged care laws bear the fingerprints of industry lobbyists. Will the voices of older Australians be heard?on April 16, 2024 at 5:47 pm
Older Australians fear their voices are being drowned out in favour of powerful industry groups who have greater influence over government.
- In search for alien life, purple may be the new greenon April 16, 2024 at 7:31 am
From house plants and gardens to fields and forests, green is the color we most associate with surface life on Earth, where conditions favored the evolution of organisms that perform oxygen-producing ...
- Ski wax contaminated Park City’s aquifers with ‘forever chemicals.’ It could cost millions to clean up.on April 15, 2024 at 5:00 am
Study finds soil at ski areas have elevated levels microplastics believed to be left by ski and snowboard wax.
- What's it like to work on Robert Pirsig's Zen motorcycle? Museum curators can tell you.on April 12, 2024 at 3:08 am
One of Pirsig's books was a 182-page Honda shop manual on how to fix the motorcycle. Smithsonian conservators found Pirsig's greasy fingerprints on inside pages with engine pistons, crankshafts and ...
- A Geological Adventure Uncovered Ancient Chunks of Earth Hiding in Crystalson April 5, 2024 at 6:00 am
By tracing the chemical fingerprint of the Finnish river sand, researchers discovered that Scandinavia originally broke off Greenland. A scientific study out of Copenhagen borrowed a script from a ...
- Plastic food packaging contains thousands of chemicals, study findson March 18, 2024 at 5:00 pm
Food packaging from five countries has complex, unique chemical fingerprints, and some items contain thousands of different chemicals, according to a new study (Environ. Sci. Technol. 2024 ...
- Forensic spray using jellyfish protein could speed up fingerprint detectionon March 2, 2024 at 9:12 pm
are increasingly restricting the use of solvents used in fingerprint detection methods, including per- and polyfluoroalkyl substances (PFAS), sometimes known as “forever chemicals”.
- Chemists develop method to take ‘chemical fingerprint’ from gin sampleson February 4, 2024 at 4:01 pm
Chemists have trialled a new technique that takes a “chemical fingerprint” of gin in seconds, which could help producers futureproof their gins and conduct quality control. A team of ...
via Google News and Bing News